All tasks
Task·audio

Text-to-Speech AI Models & Workflows

Give your workflow a voice. Pick a text-to-speech model, drop it into a NodeTool graph, and turn scripts into narration and voiceover — with your own keys.

Download NodeTool
Image To Audio StoryMusic Video VisualizerMeeting Transcript SummarizerSummarize Audio

Models for text to speech

ElevenLabs v3
audio
ElevenLabs

Expressive, multi-lingual voices with cloning.

OpenAI TTS
audio
OpenAI

Clean, reliable narration voices.

Kokoro
audio
Local (MLX)

Open-weight TTS that runs on Apple Silicon.

A workflow that does it

Workflow Editor
Note
String Input
Aurora Trail smart fitness watch — launch-week offer: 20% off. GPS navigation, heart-rate analytics, adaptive coaching, water resistance.
String Input
active millennials who hike on weekends and scroll fitness content at night
Integer Input
Image Input
Prompt
Brief
Audience
Count
You are planning a paid-social creative test for the product in the attached photo. Product and offer: {{ BRIEF }} Audience: {{ AUDIENCE }}…
Agent
Prompt
Image
Text
Prompt
Plan
Count
Audience
From this creative test plan, write exactly {{ COUNT }} spoken ad hooks, one per line — no numbering, no quotes, no labels. Rules: - One ho…
List Generator
Prompt
Preview
Prompt
Hook
Brief
Audience
One vertical 9:16 paid-social ad still, built from the input product photo. Spoken hook this scene must visualize: {{ HOOK }} Product and o…
Image To Image
Prompt
Image
Prompt
Hook
Animate this product ad still as a short vertical video. The hook spoken over it: {{ HOOK }} One subtle handheld push-in toward the product…
Image To Video
Image
Prompt
Text To Speech
Text
Audio
Add Audio
Video
Audio
Preview
Open the Ad Creative Factory template

Templates that wire text to speech

Video
Ad Creative Factory
Audio & Music
Image To Audio Story
Video
Music Video Visualizer
Audio & Music
Meeting Transcript Summarizer
Audio & Music
Podcast Repurposing Studio
Audio & Music
Summarize Audio

Frequently asked questions

What is text-to-speech?

It converts written text into spoken audio using an AI voice — useful for narration, voiceover, and accessibility.

Can I clone or customize a voice?

With providers like ElevenLabs, yes. Swap the TTS node's model and voice settings to change how it sounds.

Does it run offline?

Local models such as Kokoro run entirely in NodeTool Studio on your own machine — no network needed.

Do text to speech on your own machine

Free, open source, and yours to run. Download Studio, pick a model, and wire it into a workflow with your own keys.

Download NodeTool